Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets

Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to aid in rapid evaluation of CT scans for differentiation of COVID-19 findings from other clinical entities. Here we show that a series of deep learning algorithms, trained in a diverse international cohort of 1280 patients to localize parietal pleura/lung parenchyma followed by classification of COVID-19 pneumonia, can achieve up to 90.8% accuracy, with 84% sensitivity and 93% specificity, as evaluated in an independent test set (not included in training and validation) of 1337 patients. Normal controls included chest CTs from oncology, emergency, and pneumonia-related patients. The false positive rate in 140 patients with laboratory confirmed other (non-COVID-19) pneumonias was 10%. AI-based algorithms can readily identify CT scans with COVID-19 associated pneumonia, as well as distinguish non-COVID related pneumonias with high specificity in diverse patient populations.

Stephanie A Harmon, Thomas H Sanford, Sheng Xu, Evrim B Turkbey, Holger Roth, Ziyue Xu, Dong Yang, Andriy Myronenko, Victoria Anderson, Amel Amalu, Maxime Blain, Michael Kassin, Dilara Long, Nicole Varble, Stephanie M Walker, Ulas Baci, Anna Maria Ierardi, Elvira Stellato, Guido Giovanni Plensich, Giuseppe Franceschelli, Cristiano Girelloni, Giovanni Irmici, Dominic Labella, Dima Hammoud, Ashkan Malayeri, Elizabeth Jones, Ronald M Summers, Peter L Choyke, Daguang Xu, Mona Flores, Kaku Tamura, Hioriumi Obinata, Hitoshi Mori, Francesca Patella, Maurizio Caritati, Gianpaolo Carraieillo, Peng An, Bradford J Wood, Baris Turkbey